maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/internalize.ll

60 lines
1.9 KiB
LLVM
Raw Normal View History

AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
; RUN: opt -O1 -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-internalize-symbols < %s | FileCheck -check-prefix=ALL -check-prefix=OPT %s
; RUN: opt -O0 -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-internalize-symbols < %s | FileCheck -check-prefix=ALL -check-prefix=OPTNONE %s
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
; OPT-NOT: gvar_unused
; OPTNONE: gvar_unused
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
@gvar_unused = addrspace(1) global i32 undef, align 4
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
; ALL: gvar_used
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
@gvar_used = addrspace(1) global i32 undef, align 4
AMDGPU: Stop forcing internalize at -O0 This doesn't really matter if clang is always emitting the visibility as hidden by default. llvm-svn: 341168
2018-08-31 14:02:36 +08:00
; OPT: define internal fastcc void @func_used_noinline(
; OPT-NONE: define fastcc void @func_used_noinline(
[AMDGPU] Port of HSAIL inliner Differential Revision: https://reviews.llvm.org/D36849 llvm-svn: 313714
2017-09-20 12:25:58 +08:00
define fastcc void @func_used_noinline(i32 addrspace(1)* %out, i32 %tid) #1 {
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
entry:
store volatile i32 %tid, i32 addrspace(1)* %out
ret void
}
AMDGPU: Stop forcing internalize at -O0 This doesn't really matter if clang is always emitting the visibility as hidden by default. llvm-svn: 341168
2018-08-31 14:02:36 +08:00
; OPTNONE: define fastcc void @func_used_alwaysinline(
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
; OPT-NOT: @func_used_alwaysinline
[AMDGPU] Port of HSAIL inliner Differential Revision: https://reviews.llvm.org/D36849 llvm-svn: 313714
2017-09-20 12:25:58 +08:00
define fastcc void @func_used_alwaysinline(i32 addrspace(1)* %out, i32 %tid) #2 {
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
entry:
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
store volatile i32 %tid, i32 addrspace(1)* %out
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
ret void
}
AMDGPU: Stop forcing internalize at -O0 This doesn't really matter if clang is always emitting the visibility as hidden by default. llvm-svn: 341168
2018-08-31 14:02:36 +08:00
; OPTNONE: define void @func_unused(
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
; OPT-NOT: @func_unused
[AMDGPU] Port of HSAIL inliner Differential Revision: https://reviews.llvm.org/D36849 llvm-svn: 313714
2017-09-20 12:25:58 +08:00
define void @func_unused(i32 addrspace(1)* %out, i32 %tid) #1 {
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
entry:
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
store volatile i32 %tid, i32 addrspace(1)* %out
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
ret void
}
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
; ALL: define amdgpu_kernel void @kernel_unused(
define amdgpu_kernel void @kernel_unused(i32 addrspace(1)* %out) #1 {
entry:
store volatile i32 1, i32 addrspace(1)* %out
ret void
}
; ALL: define amdgpu_kernel void @main_kernel()
; ALL: tail call i32 @llvm.amdgcn.workitem.id.x
; ALL: tail call fastcc void @func_used_noinline
; ALL: store volatile
; ALL: ret void
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
define amdgpu_kernel void @main_kernel() {
entry:
AMDGPU: Run internalize symbols at -O0 The relocations used for externally visible functions aren't supported, so the direct call emitted ends up hitting a linker error. llvm-svn: 313616
2017-09-19 15:40:11 +08:00
%tid = tail call i32 @llvm.amdgcn.workitem.id.x()
tail call fastcc void @func_used_noinline(i32 addrspace(1)* @gvar_used, i32 %tid)
tail call fastcc void @func_used_alwaysinline(i32 addrspace(1)* @gvar_used, i32 %tid)
[AMDGPU] Internalize non-kernel symbols Since we have no call support and late linking we can produce code only for used symbols. This saves compilation time, size of the final executable, and size of any intermediate dumps. Run Internalize pass early in the opt pipeline followed by global DCE pass. To enable it RT can pass -amdgpu-internalize-symbols option. Differential Revision: https://reviews.llvm.org/D29214 llvm-svn: 293549
2017-01-31 05:05:18 +08:00
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #0
attributes #0 = { nounwind readnone }
[AMDGPU] Port of HSAIL inliner Differential Revision: https://reviews.llvm.org/D36849 llvm-svn: 313714
2017-09-20 12:25:58 +08:00
attributes #1 = { noinline nounwind }
attributes #2 = { alwaysinline nounwind }